Texture statistics for classification of land use with multitemporal JERS-1 SAR single-look imagery

Author

Kurosu, Takashi ; Uratsuka, Seiho ; Maeno, Hideo ; Kozu, Toshiaki

Author_Institution

Commun. Res. Lab., Minist. of Posts & Telecommun., Tokyo, Japan

Volume

37

Issue

1

fYear

1999

fDate

1/1/1999 12:00:00 AM

Firstpage

227

Lastpage

235

Abstract

Texture statistics are studied using multitemporal JERS-1 synthetic aperture radar (SAR) single-look imagery. A correct autocorrelation function of texture is derived and utilized to calculate textural features. It is demonstrated that a significant improvement in the classification accuracy results if the textural features are used as additional inputs to the classifier

Keywords

geophysical signal processing; geophysical techniques; image classification; image sequences; image texture; radar imaging; remote sensing by radar; spaceborne radar; synthetic aperture radar; terrain mapping; JERS-1; SAR; autocorrelation function; geophysical measurement technique; image classification; image sequence; image texture statistics; land surface; land use; multitemporal images; radar imaging; radar remote sensing; single-look imagery; spaceborne radar; synthetic aperture radar; terrain mapping; textural feature; Autocorrelation; Azimuth; Data acquisition; Fading; Image analysis; Image texture analysis; Remote sensing; Statistics; Synthetic aperture radar; Testing;

fLanguage

English

Journal_Title

Geoscience and Remote Sensing, IEEE Transactions on

Publisher

ieee

ISSN

0196-2892

Type

jour

DOI

10.1109/36.739157

Filename

739157